Environment:
	Python: 3.10.11
	PyTorch: 2.0.1
	Torchvision: 0.15.2
	CUDA: 11.7
	CUDNN: 8500
	NumPy: 1.24.3
	PIL: 9.4.0
	Testing environment: [2]
Args:
	algorithm: Selective_KD
	checkpoint_freq: 300
	data_dir: ./domainbed/data
	dataset: PACS
	holdout_fraction: 0.2
	hparams: {
    "resnet18": false,
    "resnet_dropout": 0,
    "nonlinear_classifier": false,
    "data_augmentation": true,
    "clip_backbone": "ViT-B/32",
    "student_model": "resnet",
    "SMA": true,
    "batch_size": 32
}
	hparams_seed: 2
	output_dir: sweep/ablation3/outputs/0e01bebc200ef6566e389665456b0493
	save_linear_probed_clip: False
	save_model_every_checkpoint: False
	seed: 1727342536
	skip_model_save: False
	steps: 5001
	sweep: True
	task: domain_generalization
	test_envs: [2]
	trial_seed: 1
	uda_holdout_fraction: 0
	visualize: False
Not saving models
HParams:
	SMA: True
	batch_size: 32
	class_balanced: False
	clip_backbone: ViT-B/32
	data_augmentation: True
	lambda1: 0.5439617198173775
	lambda2: 0.5509403872292429
	last_k_epoch: 0.38252238504986713
	lr: 5e-05
	nonlinear_classifier: False
	resnet18: False
	resnet_dropout: 0
	student_model: resnet
	temperature: 4.920147743151585
	weight_decay: 1e-06
	worst_case_p: 0.3
using augment transform
using augment transform
using normal transform
using augment transform
using device:  cuda
Using ViT-B/32...
constructing student model
using resnet 50
Using SMA
n_steps 5001
checkpoint_freq 300
agg_test_acc  agg_val_acc   env0_in_acc   env0_out_acc  env1_in_acc   env1_out_acc  env2_in_acc   env2_out_acc  env3_in_acc   env3_out_acc  epoch         loss          mem_gb        step          step_time    
0.1571856287  0.1930378077  0.1653447224  0.1907090465  0.1567164179  0.1794871795  0.1646706587  0.1497005988  0.1984732824  0.2089171975  0.0000000000  6.5609374046  2.1691875458  0             1.5319149494 
0.9891467061  0.9487167948  0.9829164124  0.9462102689  0.9824093817  0.9572649573  0.9872754491  0.9910179641  0.9564249364  0.9426751592  7.1856287425  2.2635834666  2.4361939430  300           0.1568043764 
0.9895209576  0.9601404231  0.9957291031  0.9608801956  0.9946695096  0.9679487179  0.9910179641  0.9880239521  0.9799618321  0.9515923567  14.371257485  0.9547562021  2.4361939430  600           0.1759692057 
0.9906437121  0.9594488235  0.9969493594  0.9584352078  0.9946695096  0.9594017094  0.9902694611  0.9910179641  0.9828244275  0.9605095541  21.556886227  0.7924563400  2.4361939430  900           0.1733477028 
0.9902694606  0.9655371966  0.9981696156  0.9608801956  0.9984008529  0.9764957265  0.9895209581  0.9910179641  0.9891857506  0.9592356688  28.742514970  0.7351887822  2.4361939430  1200          0.1732815409 
0.9891467061  0.9641469939  0.9987797437  0.9486552567  0.9994669510  0.9743589744  0.9902694611  0.9880239521  0.9917302799  0.9694267516  35.928143712  0.7140558853  2.4361939430  1500          0.1725015640 
0.9872754486  0.9617911037  0.9993898719  0.9535452323  0.9989339019  0.9636752137  0.9895209581  0.9850299401  0.9910941476  0.9681528662  43.113772455  0.6898540456  2.4361939430  1800          0.1723277775 
0.9865269456  0.9649962131  0.9993898719  0.9584352078  0.9984008529  0.9722222222  0.9880239521  0.9850299401  0.9933206107  0.9643312102  50.299401197  0.6570906730  2.4361939430  2100          0.1722758881 
0.9872754486  0.9684753348  1.0000000000  0.9633251834  0.9989339019  0.9764957265  0.9895209581  0.9850299401  0.9949109415  0.9656050955  57.485029940  0.6252941863  2.4361939430  2400          0.1736361456 
0.9887724546  0.9678109550  0.9993898719  0.9608801956  0.9994669510  0.9807692308  0.9895209581  0.9880239521  0.9955470738  0.9617834395  64.670658682  0.6204311632  2.4361939430  2700          0.1728382222 
0.9887724546  0.9706805712  1.0000000000  0.9682151589  0.9989339019  0.9807692308  0.9895209581  0.9880239521  0.9945928753  0.9630573248  71.856287425  0.6006372026  2.4361939430  3000          0.1731887046 
0.9887724546  0.9678316061  1.0000000000  0.9584352078  0.9978678038  0.9743589744  0.9895209581  0.9880239521  0.9958651399  0.9707006369  79.041916167  0.4897098585  5.3991427422  3300          0.1977752709 
0.9887724546  0.9701738109  1.0000000000  0.9731051345  0.9994669510  0.9743589744  0.9895209581  0.9880239521  0.9971374046  0.9630573248  86.227544910  0.3872798031  5.3991427422  3600          0.2068133537 
0.9887724546  0.9711051996  1.0000000000  0.9682151589  1.0000000000  0.9807692308  0.9895209581  0.9880239521  0.9977735369  0.9643312102  93.413173652  0.3618979436  5.3991427422  3900          0.2053261614 
0.9887724546  0.9629415928  1.0000000000  0.9535452323  1.0000000000  0.9722222222  0.9895209581  0.9880239521  0.9961832061  0.9630573248  100.59880239  0.3479888515  5.3991427422  4200          0.2049998474 
0.9887724546  0.9692218465  0.9987797437  0.9608801956  0.9989339019  0.9786324786  0.9895209581  0.9880239521  0.9955470738  0.9681528662  107.78443113  0.3342892354  5.3991427422  4500          0.2048482633 
0.9883982031  0.9690505793  1.0000000000  0.9633251834  0.9994669510  0.9807692308  0.9887724551  0.9880239521  0.9971374046  0.9630573248  114.97005988  0.3248363984  5.3991427422  4800          0.2039371697 
0.9883982031  0.9697970910  0.9987797437  0.9608801956  1.0000000000  0.9829059829  0.9887724551  0.9880239521  0.9977735369  0.9656050955  119.76047904  0.3155160190  5.3991427422  5000          0.2067449117 
